Returns initiate

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is highly transparent about side effects and consequences: it creates a return, triggers a seller-funded label obligation, may lead to auto-refund, and states idempotency on order_id. This goes well beyond the annotations (readOnlyHint: false, idempotentHint: true) and gives the agent a clear picture of the tool's behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is unnecessarily verbose and redundant. The full policy (30-day window, free, full refund, no restocking fee, seller funds label) is repeated nearly verbatim twice. The first paragraph already conveys all necessary information; the second paragraph adds no new content. This reduces clarity and increases token usage.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (3 params, 1 enum, no output schema), the description covers all essential context: initiation condition, policy rules, reason semantics, post-return obligations (label upload, auto-refund), and idempotency. No critical operational detail is missing for an agent to invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the tool description adds meaningful policy context for the reason enum (e.g., cooling_off_statutory corresponds to days 0–14 change-of-mind, defective is a CRA 2015 claim). This enriches the schema's per-parameter descriptions and clarifies how each reason affects the return process.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Initiate a return on a delivered order.' It distinguishes this state-changing action from read-only sibling tools like returns_get, returns_list, and returns_get_label by using the verb 'Initiate' and specifying the precondition (delivered order).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear when-to-use condition ('on a delivered order') and details the applicable policies (30-day window, free return, seller-funded label). It does not explicitly mention alternatives such as returns_get or seller_accept_return, but the sibling context and verb 'Initiate' make the intended usage clear. A minor gap is the lack of an explicit 'do not use for read-only checks.'

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.